1. Prediction of local relapse and distant metastasis in patients with definitive chemoradiotherapy-treated cervical cancer by deep learning from [ 18 F]-fluorodeoxyglucose positron emission tomography/computed tomography.
- Author
-
Shen WC, Chen SW, Wu KC, Hsieh TC, Liang JA, Hung YC, Yeh LS, Chang WC, Lin WC, Yen KY, and Kao CH
- Subjects
- Adult, Aged, Aged, 80 and over, Cervix Uteri diagnostic imaging, Cervix Uteri pathology, Cohort Studies, Female, Humans, Middle Aged, Prognosis, Radiopharmaceuticals, Recurrence, Retrospective Studies, Sensitivity and Specificity, Treatment Outcome, Uterine Cervical Neoplasms pathology, Chemoradiotherapy methods, Deep Learning, Fluorodeoxyglucose F18, Neoplasm Recurrence, Local diagnostic imaging, Positron Emission Tomography Computed Tomography methods, Uterine Cervical Neoplasms diagnostic imaging, Uterine Cervical Neoplasms therapy
- Abstract
Background: We designed a deep learning model for assessing
18 F-FDG PET/CT for early prediction of local and distant failures for patients with locally advanced cervical cancer., Methods: All 142 patients with cervical cancer underwent18 F-FDG PET/CT for pretreatment staging and received allocated treatment. To augment the amount of image data, each tumor was represented as 11 slice sets each of which contains 3 2D orthogonal slices to acquire a total of 1562 slice sets. In each round of k-fold cross-validation, a well-trained proposed model and a slice-based optimal threshold were derived from a training set and used to classify each slice set in the test set into the categories of with or without local or distant failure. The classification results of each tumor were aggregated to summarize a tumor-based prediction result., Results: In total, 21 and 26 patients experienced local and distant failures, respectively. Regarding local recurrence, the tumor-based prediction result summarized from all test sets demonstrated that the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 71%, 93%, 63%, 95%, and 89%, respectively. The corresponding values for distant metastasis were 77%, 90%, 63%, 95%, and 87%, respectively., Conclusion: This is the first study to use deep learning model for assessing18 F-FDG PET/CT images which is capable of predicting treatment outcomes in cervical cancer patients., Key Points: • This is the first study to use deep learning model for assessing18 F-FDG PET/CT images which is capable of predicting treatment outcomes in cervical cancer patients. • All 142 patients with cervical cancer underwent18 F-FDG PET/CT for pretreatment staging and received allocated treatment. To augment the amount of image data, each tumor was represented as 11 slice sets each of which contains 3 2D orthogonal slices to acquire a total of 1562 slice sets. • For local recurrence, all test sets demonstrated that the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 71%, 93%, 63%, 95%, and 89%, respectively. The corresponding values for distant metastasis were 77%, 90%, 63%, 95%, and 87%, respectively.- Published
- 2019
- Full Text
- View/download PDF